The SWIFTe-LDE4 ensemble achieved the best calibration after temperature scaling but still exhibited residual miscalibration with an expected calibration error of 0.217

SWIFTe-LDE4 achieved the lowest calibration errors among the four configurations after temperature scaling (expected calibration error, 0.217; Brier score, 0.222), although the absolute expected calibration error indicates residual miscalibration

http://arxiv.org/abs/2608.27178v1